← BACK TO LAB INDEX EXP_ID // 01
Agent Architecture · ACTIVE
Agent Memory
Exploring persistent episodic memory and state compactors for multi-turn autonomous coding agents.
TELEMETRY: 1.83s · 4 tools · 12k tokens
TOOLS: Python pgvector LangGraph Embeddings
Hypothesis & Experiment
Can we preserve long-term agent context across 500+ turns without linear token cost growth or degradation of historical reasoning?
Methodology
We test hierarchical compaction where raw tool input/outputs are summarized asynchronously into an immutable knowledge graph while retaining strict constraint keys.
Observations
- Fact preservation improved by 41% compared to sliding-window context buffers.
- Sub-graph queries against indexed decisions yielded sub-25ms retrieval.